Transformers
Safetensors

Configuration Parsing Warning:Invalid JSON for config file config.json

How to Get Started with the Model

Use the code below to get started with the model.

import torch  
from transformers import AutoTokenizer  
from transformers import Mamba2ForCausalLM


if __name__ == "__main__":
    device = "cuda"
    model_id = "benchang1110/mamba2-370m-hf"
    tokenizer = AutoTokenizer.from_pretrained(model_id)
    model = Mamba2ForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map=device)
    model.eval()

    with torch.no_grad():
      text = input("Input: ")
      input_ids = tokenizer(text, return_tensors="pt").to(device)
      output = model.generate(**input_ids, max_new_tokens=1024, do_sample=False)
      print(tokenizer.decode(output[0], skip_special_tokens=True))

Conversion script: mamba2hf.py

Downloads last month
43
Safetensors
Model size
0.4B params
Tensor type
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for benchang1110/mamba2-370m-hf

Finetuned
(3)
this model

Collection including benchang1110/mamba2-370m-hf